Package: transformerForecasting
Type: Package
Title: Transformer Deep Learning Model for Time Series Forecasting
Version: 0.1.0
Authors@R: c(person("G H", "Harish Nayak",  role = c("aut", "cre"),   email = "harishnayak626@gmail.com"), person("Md Wasi Alam",  role = c("ths"), email = "mw.Alam@icar.gov.in"), person("B Samuel Naik", role = c("ctb"), email = "banavathsamuelnaik@gmail.com"), person("G Avinash", role = c("ctb"), email = "avinash143stat@gmail.com"), person("Kabilan", "S", role = c("ctb"), email = "kabilan151414@gmail.com"), person("Varshini B S", role = c("ctb"), email = "varshinibs29@gmail.com"), person("Mrinmoy Ray", role = c("ths"), email = "mrinmoy4848@gmail.com"),person("Rajeev Ranjan Kumar", role = c("ths"), email = "rrk.uasd@gmail.com"))
Maintainer: G H Harish Nayak <harishnayak626@gmail.com>
Description: Time series forecasting faces challenges due to the non-stationarity, nonlinearity, and chaotic nature of the data. Traditional deep learning models like Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) process data sequentially but are inefficient for long sequences. To overcome the limitations of these models, we proposed a transformer-based deep learning architecture utilizing an attention mechanism for parallel processing, enhancing prediction accuracy and efficiency. This paper presents user-friendly code for the implementation of the proposed transformer-based deep learning architecture utilizing an attention mechanism for parallel processing. References:  Nayak et al. (2024) <doi:10.1007/s40808-023-01944-7> and Nayak et al. (2024) <doi:10.1016/j.simpa.2024.100716>.
Imports: ggplot2, keras, tensorflow, magrittr, reticulate (>= 1.20)
Suggests: dplyr, knitr, lubridate, readr, rmarkdown, utils
License: GPL-3
Encoding: UTF-8
RoxygenNote: 7.3.2
Author: G H Harish Nayak [aut, cre],
  Md Wasi Alam [ths],
  B Samuel Naik [ctb],
  G Avinash [ctb],
  Kabilan S [ctb],
  Varshini B S [ctb],
  Mrinmoy Ray [ths],
  Rajeev Ranjan Kumar [ths]
Depends: R (>= 4.0.0)
LazyData: true
VignetteBuilder: knitr
NeedsCompilation: no
Packaged: 2025-03-05 04:28:04 UTC; kabil
Repository: CRAN
Date/Publication: 2025-03-07 11:10:06 UTC
Built: R 4.5.2; ; 2025-11-08 03:52:41 UTC; windows
